© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 2-ATT-KK
    6. 22008
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate plans or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.19
    3:0.04
    4:0.25
    5:0.06
    6:0.02
    7:0.01
    8:0.16
    9:0.11
    10:0.04
    11:0.02
    Negative Logits
     whiff
    -1.35
    laugh
    -1.34
    Member
    -1.34
    Elf
    -1.32
    Fe
    -1.30
     Nicholson
    -1.28
    leon
    -1.28
    staff
    -1.26
     Feldman
    -1.24
     Leap
    -1.24
    POSITIVE LOGITS
     ACTIONS
    1.76
    arenthood
    1.67
     arrang
    1.51
     warr
    1.41
     rul
    1.41
     agre
    1.40
     enlarg
    1.39
     withd
    1.37
     continu
    1.36
     topp
    1.32
    Activations Density 0.010%

    No Known Activations